Method and System for Piracy Detection

1. A system comprising: a storage device and a memory operative to store a plurality of target content items comprising an original content item and additional versions of the original content item; a comparator configured to execute a process, wherein the process is operative to: perform a first iteration of comparison by comparing the original content item with one or more of the additional versions of the original content item, perform a second iteration of comparison by comparing particular one of the additional versions of the original content item with at least one other of the additional versions of the original content item, based on the first and second iterations of comparison, develop a correlation graph indicating at least a level of correlation between the original content item and the one or more of the additional versions of the original content item and a level of correlation between the particular one of the additional versions of the original content item and the at least one other of the additional versions of the original content item, and generate training data comprising a set of correlation graphs that includes the correlation graph; and a machine learning system that is trained using the generated training data, wherein the trained machine learning system is operative to: receive, as an input, the correlation graph, and output a decision which indicates, based on the levels of correlation indicated by the correlation graph, which of the additional versions of the original content item are pirated content items or non-pirated content items.

2. The system according to claim 1 wherein the comparator is controlled by a processor.

3. The system according to claim 1 wherein the machine learning system comprises a neural network.

4. The system according to claim 1 wherein the machine learning system comprises a neural network which is built as a result of being trained.

5. The system according to claim 1 wherein the machine learning system comprises a naïve Bayesian classification system.

6. The system according to claim 1 wherein the machine learning system comprises a system implementing a clustering algorithm.

7. The system according to claim 1 wherein a node of the correlation graph represents one of the content items, and a length of an edge between two nodes of the correlation graph represents a similarity factor between two content items represented by the two nodes.

8. The system according to claim 7 wherein two content items of the plurality of target content items having a first similarity factor are graphed as two nodes with a smaller distance between them than two nodes representing two content items of the plurality of target content items having a second similarity factor, wherein the first similarity factor is higher than the second similarity factor.

9. A method comprising: storing a plurality of target content items in a storage device associated with a memory, the plurality of target content items comprising an original content item and additional versions of the original content item; performing, by a comparator, a first iteration of comparison by comparing the original content item with one or more of the additional versions of the original content item; performing, by the comparator, a second iteration of comparison by comparing a particular one of the additional versions of the original content item with at least one other of the additional versions of the original content item; based on the first and second iterations of comparison, developing, by the comparator, a correlation graph indicating at least a level of correlation between the original content item and the one or more of the additional versions of the original content item and a level of correlation between the particular one of the additional versions of the original content item and the at least one other of the additional versions of the original content item; generating, by the comparator, training data comprising a set of correlation graphs that includes the correlation graph; training, by the comparator, a machine learning system using the generated training data; after the training of the machine learning system, inputting the correlation graph into the machine learning system; and outputting a decision from the machine learning system, the decision indicating based on the levels of correlation indicated by the correlation graph, which of the additional versions of the original content item are pirated content items or non-pirated content items.

10. The method according to claim 9 wherein the comparator is controlled by a processor.

11. The method according to claim 9 wherein the machine learning system comprises a neural network.

12. The method according to claim 9 wherein the machine learning system comprises a neural network which is built as a result of being trained.

13. The method according to claim 9 wherein the machine learning system comprises a naïve Bayesian classification machine learning system.

14. The method according to claim 9 wherein the machine learning system comprises a clustering algorithm machine learning system.

15. The method according to claim 9 wherein a node of the correlation graph represents one of the content items, and a length of an edge between two nodes of the correlation graph represents a similarity factor between two content items represented by the two nodes.

16. The method according to claim 15 wherein two content items of the plurality of target content items having a first similarity factor are graphed as two nodes with a smaller distance between them than two nodes representing two content items of the plurality of target content items having a second similarity factor, wherein the first similarity factor is higher than the second similarity factor.